--- documentViewer/MpdlXmlTextServer.py	2010/06/18 14:08:46	1.5
+++ documentViewer/MpdlXmlTextServer.py	2011/02/14 14:41:12	1.225
@@ -1,16 +1,15 @@
 
 from OFS.SimpleItem import SimpleItem
 from Products.PageTemplates.PageTemplateFile import PageTemplateFile 
-
 from Ft.Xml import EMPTY_NAMESPACE, Parse
 
+import md5
 import sys
 import logging
 import urllib
 import documentViewer
 from documentViewer import getTextFromNode, serializeNode
 
-
 class MpdlXmlTextServer(SimpleItem):
     """TextServer implementation for MPDL-XML eXist server"""
     meta_type="MPDL-XML TextServer"
@@ -30,41 +29,49 @@ class MpdlXmlTextServer(SimpleItem):
             self.serverUrl = serverUrl
         else:
             self.serverUrl = "http://%s/mpdl/interface/"%serverName
-
         
     def getHttpData(self, url, data=None):
         """returns result from url+data HTTP request"""
         return documentViewer.getHttpData(url,data,timeout=self.timeout)
-
     
     def getServerData(self, method, data=None):
         """returns result from text server for method+data"""
         url = self.serverUrl+method
         return documentViewer.getHttpData(url,data,timeout=self.timeout)
 
-
-    def getSearch(self, pn=1, pageinfo=None,  docinfo=None, query=None, queryType=None, lemma=None):
+    def getSearch(self, pageinfo=None,  docinfo=None,   lemma=None):
         """get search list"""
         docpath = docinfo['textURLPath'] 
         url = docinfo['url']
-        logging.debug("documentViewer (gettoc) docpath: %s"%(docpath))
-        logging.debug("documentViewer (gettoc) url: %s"%(url))
         pagesize = pageinfo['queryPageSize']
-        pn = pageinfo['searchPN']
+        pn = pageinfo.get('searchPN',1)
         sn = pageinfo['sn']
         highlightQuery = pageinfo['highlightQuery']
         query =pageinfo['query']
         queryType =pageinfo['queryType']
         viewMode=  pageinfo['viewMode']
         tocMode = pageinfo['tocMode']
+        characterNormalization = pageinfo['characterNormalization']
+        optionToggle = pageinfo['optionToggle']
         tocPN = pageinfo['tocPN']
         selfurl = self.absolute_url()
-        
-        data = self.getServerData("doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&sn=%s&viewMode=%s&highlightQuery=%s"%(docpath, 'text', queryType, query, pagesize, pn, sn, viewMode,highlightQuery))
-        #page=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&sn=%s&viewMode=%s&highlightQuery=%s"%(docpath, 'text', queryType, query, pagesize, pn, sn, viewMode,highlightQuery) ,outputUnicode=False)                
-        
+        data = self.getServerData("doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&sn=%s&viewMode=%s&characterNormalization=%s&optionToggle=%s&highlightQuery=%s"%(docpath, 'text', queryType, urllib.quote(query), pagesize, pn, sn, viewMode,characterNormalization,optionToggle ,urllib.quote(highlightQuery)))
         pagexml = data.replace('?document=%s'%str(docpath),'?url=%s'%url)
         pagedom = Parse(pagexml)
+        
+        """
+        pagedivs = pagedom.xpath("//div[@class='queryResultHits']") 
+        if (pagedivs == pagedom.xpath("//div[@class='queryResultHits']")):
+            if len(pagedivs)>0:
+                docinfo['queryResultHits'] = int(getTextFromNode(pagedivs[0]))
+                s = getTextFromNode(pagedivs[0])
+                s1 = int(s)/10+1
+                try:
+                    docinfo['queryResultHits'] = int(s1)
+                    logging.debug("SEARCH ENTRIES: %s"%(s1))
+                except:
+                    docinfo['queryResultHits'] = 0
+        """
         if (queryType=="fulltext")or(queryType=="xpath")or(queryType=="xquery")or(queryType=="fulltextMorphLemma"):   
             pagedivs = pagedom.xpath("//div[@class='queryResultPage']")
             if len(pagedivs)>0:
@@ -76,8 +83,9 @@ class MpdlXmlTextServer(SimpleItem):
                         href = hrefNode.nodeValue
                         if href.startswith('page-fragment.xql'):
                             selfurl = self.absolute_url()            
-                            pagexml=href.replace('mode=text','mode=texttool&viewMode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&tocMode=%s&searchPN=%s&tocPN=%s'%(viewMode,queryType,query,pagesize,pn,tocMode,pn,tocPN))
+                            pagexml=href.replace('mode=text','mode=texttool&viewMode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&tocMode=%s&searchPN=%s&tocPN=%s&optionToggle=%s&characterNormalization=%s'%(viewMode,queryType,urllib.quote(query),pagesize,pn,tocMode,pn,tocPN,optionToggle,characterNormalization))
                             hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl)                                           
+                logging.debug("PUREXML :%s"%(serializeNode(pagenode)))
                 return serializeNode(pagenode)        
         if (queryType=="fulltextMorph"):
             pagedivs = pagedom.xpath("//div[@class='queryResult']")
@@ -90,13 +98,13 @@ class MpdlXmlTextServer(SimpleItem):
                         href = hrefNode.nodeValue
                         if href.startswith('page-fragment.xql'):
                             selfurl = self.absolute_url()       
-                            pagexml=href.replace('mode=text','mode=texttool&viewMode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&tocMode=%s&searchPN=%s&tocPN=%s'%(viewMode,queryType,query,pagesize,pn,tocMode,pn,tocPN))
+                            pagexml=href.replace('mode=text','mode=texttool&viewMode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s&tocMode=%s&searchPN=%s&tocPN=%s&optionToggle=%s&characterNormalization=%s'%(viewMode,queryType,urllib.quote(query),pagesize,pn,tocMode,pn,tocPN,optionToggle,characterNormalization))
                             hrefNode.nodeValue = pagexml.replace('page-fragment.xql','%s'%selfurl)  
                         if href.startswith('../lt/lemma.xql'):
                             hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_lemma_New'%(selfurl))        
                             l.setAttributeNS(None, 'target', '_blank')
                             l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;")
-                            l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')  
+                            l.setAttributeNS(None, 'onClick', 'popupWin.focus();')  
                 pagedivs = pagedom.xpath("//div[@class='queryResultMorphExpansion']")                
                 return serializeNode(pagenode)        
         if (queryType=="ftIndex")or(queryType=="ftIndexMorph"):
@@ -108,39 +116,79 @@ class MpdlXmlTextServer(SimpleItem):
                     hrefNode = l.getAttributeNodeNS(None, u"href")
                     if hrefNode:
                         href = hrefNode.nodeValue
-                        hrefNode.nodeValue=href.replace('mode=text','mode=texttool&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s'%(viewMode,tocMode,tocPN,pn))             
+                        hrefNode.nodeValue=href.replace('mode=text','mode=texttool&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s&optionToggle=%s&characterNormalization=%s'%(viewMode,tocMode,tocPN,pn,optionToggle,characterNormalization))             
                         if href.startswith('../lt/lex.xql'):
                             hrefNode.nodeValue = href.replace('../lt/lex.xql','%s/template/head_main_voc'%selfurl)         
                             l.setAttributeNS(None, 'target', '_blank')
                             l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;")
-                            l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
+                            l.setAttributeNS(None, 'onClick', 'popupWin.focus();')
                         if href.startswith('../lt/lemma.xql'):
                             hrefNode.nodeValue = href.replace('../lt/lemma.xql','%s/template/head_main_lemma'%selfurl)        
                             l.setAttributeNS(None, 'target', '_blank')
                             l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=400, scrollbars=1'); return false;")
-                            l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')
+                            l.setAttributeNS(None, 'onClick', 'popupWin.focus();')
                 return serializeNode(pagenode)      
         return "no text here"   
                        
-    def getNumPages(self, docinfo):
-        """get list of pages from fulltext and put in docinfo"""
-        if 'numPages' in docinfo:
-            # already there
-            return docinfo
-        
-        xquery = '//pb'
-        text = self.getServerData("xquery.xql","document=%s&xquery=%s"%(docinfo['textURLPath'],xquery))
-        #text = self.template.fulltextclient.eval("/mpdl/interface/xquery.xql", "document=%s&xquery=%s"%(docinfo['textURLPath'],xquery))
-        docinfo['numPages'] = text.count("<pb ")
-        return docinfo
-       
-    def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None, highlightQuery=None,sn=None, viewMode=None, tocMode=None, tocPN=None):
+           
+    def getGisPlaces(self, docinfo=None, pageinfo=None):
+        """ Show all Gis Places of whole Page"""
+        xpath='//place'
+        docpath = docinfo.get('textURLPath',None)
+        if not docpath:
+            return None
+
+        url = docinfo['url']
+        selfurl = self.absolute_url()
+        pn = pageinfo['current']
+        hrefList=[]
+        myList= ""
+        text=self.getServerData("xpath.xql", "document=%s&xpath=%s&pn=%s"%(docinfo['textURLPath'],xpath,pn))
+        dom = Parse(text)
+        result = dom.xpath("//result/resultPage/place")
+        for l in result:
+            hrefNode= l.getAttributeNodeNS(None, u"id")
+            href= hrefNode.nodeValue
+            hrefList.append(href)
+            myList = ",".join(hrefList)
+        logging.debug("getGisPlaces :%s"%(myList))                             
+        return myList
+    
+    def getAllGisPlaces (self, docinfo=None, pageinfo=None):
+        """Show all Gis Places of whole Book """
+        xpath ='//echo:place'
+        docpath =docinfo['textURLPath']
+        url = docinfo['url']
+        selfurl =self.absolute_url()
+        pn =pageinfo['current']
+        hrefList=[]
+        myList=""
+        text=self.getServerData("xpath.xql", "document=%s&xpath=%s"%(docinfo['textURLPath'],xpath))
+        dom =Parse(text)
+        result = dom.xpath("//result/resultPage/place")
+        
+        for l in result:
+            hrefNode = l.getAttributeNodeNS(None, u"id")
+            href= hrefNode.nodeValue
+            hrefList.append(href)
+            myList = ",".join(hrefList)
+            logging.debug("getALLGisPlaces :%s"%(myList))
+        return myList
+          
+           
+    def getTextPage(self, mode="text", pn=1, docinfo=None, pageinfo=None):
         """returns single page from fulltext"""
         docpath = docinfo['textURLPath']
         path = docinfo['textURLPath']
-        url = docinfo['url']
+        url = docinfo.get('url',None)
+        name = docinfo.get('name',None)
+        pn =pageinfo['current']
         viewMode= pageinfo['viewMode']
+        sn = pageinfo['sn']
+        highlightQuery = pageinfo['highlightQuery']
+        #mode = pageinfo ['viewMode']
         tocMode = pageinfo['tocMode']
+        characterNormalization=pageinfo['characterNormalization']
         tocPN = pageinfo['tocPN']
         selfurl = self.absolute_url()   
         if mode == "text_dict":
@@ -148,18 +196,104 @@ class MpdlXmlTextServer(SimpleItem):
         else:
             textmode = mode
         
-        textParam = "document=%s&mode=%s&pn=%s"%(docpath,textmode,pn)
+        textParam = "document=%s&mode=%s&pn=%s&characterNormalization=%s"%(docpath,textmode,pn,characterNormalization)
         if highlightQuery is not None:
-            textParam +="&highlightQuery=%s&sn=%s"%(highlightQuery,sn)           
+            textParam +="&highlightQuery=%s&sn=%s"%(urllib.quote(highlightQuery),sn)           
         
         pagexml = self.getServerData("page-fragment.xql",textParam)
-        #pagexml=self.template.fulltextclient.eval("/mpdl/interface/page-fragment.xql", textParam, outputUnicode=False)
+        dom = Parse(pagexml)
+        
+        #original Pages
+        pagedivs = dom.xpath("//div[@class='pageNumberOrig']")
+        if pagedivs == dom.xpath("//div[@class='pageNumberOrig']"):
+            if len(pagedivs)>0:
+                docinfo['pageNumberOrig']= getTextFromNode(pagedivs[0])
+                logging.debug("ORIGINAL PAGES: %s"%(docinfo['pageNumberOrig']))
+                          
+        #figureEntries
+        pagedivs = dom.xpath("//div[@class='countFigureEntries']")
+        if pagedivs == dom.xpath("//div[@class='countFigureEntries']"):
+            if len(pagedivs)>0:
+                docinfo['countFigureEntries'] = getTextFromNode(pagedivs[0])
+                s = getTextFromNode(pagedivs[0])
+                if s=='0':
+                    try:
+                        docinfo['countFigureEntries'] = int(s)
+                        logging.debug("FIGURE ENTRIES: %s"%(s))
+                    except:
+                        docinfo['countFigureEntries'] = 0
+                else:
+                    s1 = int(s)/30+1
+                    try:
+                        docinfo['countFigureEntries'] = int(s1)
+                        logging.debug("FIGURE ENTRIES: %s"%(s1))
+                    except:
+                        docinfo['countFigureEntries'] = 0      
+        
+        #allPlaces
+        pagedivs = dom.xpath("//div[@class='countPlaces']")
+        if pagedivs == dom.xpath("//div[@class='countPlaces']"):
+            if len(pagedivs)>0:
+                docinfo['countPlaces']= getTextFromNode(pagedivs[0])
+                s = getTextFromNode(pagedivs[0])
+                try:
+                    docinfo['countPlaces'] = int(s)
+                    logging.debug("PLACES HERE: %s"%(s))
+                except:
+                    docinfo['countPlaces'] = 0
+        
+        #tocEntries
+        pagedivs = dom.xpath("//div[@class='countTocEntries']")
+        if pagedivs == dom.xpath("//div[@class='countTocEntries']"):
+            if len(pagedivs)>0:
+                docinfo['countTocEntries'] = int(getTextFromNode(pagedivs[0]))
+                s = getTextFromNode(pagedivs[0])
+                if s=='0':
+                    try:
+                        docinfo['countTocEntries'] = int(s)
+                        logging.debug("TEXT ENTRIES: %s"%(s))
+                    except:
+                        docinfo['countTocEntries'] = 0
+                else:
+                    s1 = int(s)/30+1
+                    try:
+                        docinfo['countTocEntries'] = int(s1)
+                        logging.debug("TEXT ENTRIES: %s"%(s1))
+                    except:
+                        docinfo['countTocEntries'] = 0
+        
+        #numTextPages
+        pagedivs = dom.xpath("//div[@class='countPages']")
+        if pagedivs == dom.xpath("//div[@class='countPages']"):
+            if len(pagedivs)>0:
+                docinfo['numPages'] = getTextFromNode(pagedivs[0])
+                s = getTextFromNode(pagedivs[0])
+                
+                try:
+                    docinfo['numPages'] = int(s)
+                    logging.debug("PAGE NUMBER: %s"%(s))
+                
+                    np = docinfo['numPages']
+                    pageinfo['end'] = min(pageinfo['end'], np)
+                    pageinfo['numgroups'] = int(np / pageinfo['groupsize'])
+                    if np % pageinfo['groupsize'] > 0:
+                        pageinfo['numgroups'] += 1                
+                except:
+                    docinfo['numPages'] = 0
+                  
+        else:
+         #no full text -- init to 0
+            docinfo['pageNumberOrig'] = 0
+            docinfo['countFigureEntries'] = 0
+            docinfo['countPlaces'] = 0
+            docinfo['countTocEntries'] = 0
+            docinfo['numPages'] = 0
+        #return docinfo
         
-        pagedom = Parse(pagexml)
         # plain text mode
         if mode == "text":
             # first div contains text
-            pagedivs = pagedom.xpath("/div")
+            pagedivs = dom.xpath("/div")
             if len(pagedivs) > 0:      
                 pagenode = pagedivs[0]
                 links = pagenode.xpath("//a")
@@ -172,20 +306,35 @@ class MpdlXmlTextServer(SimpleItem):
                 return serializeNode(pagenode)
         if mode == "xml":
               # first div contains text
-              pagedivs = pagedom.xpath("/div")
+              pagedivs = dom.xpath("/div")
+              if len(pagedivs) > 0:
+                  pagenode = pagedivs[0]
+                  return serializeNode(pagenode)
+        if mode == "gis":
+              # first div contains text
+              pagedivs = dom.xpath("/div")
               if len(pagedivs) > 0:
                   pagenode = pagedivs[0]
+                  links =pagenode.xpath("//a")
+                  for l in links:
+                      hrefNode =l.getAttributeNodeNS(None, u"href")
+                      if hrefNode:
+                          href=hrefNode.nodeValue
+                          if href.startswith('http://chinagis.mpiwg-berlin.mpg.de'):
+                              hrefNode.nodeValue =href.replace('chinagis_REST/REST/db/chgis/mpdl','chinagis/REST/db/mpdl/%s'%name)
+                              l.setAttributeNS(None, 'target', '_blank') 
                   return serializeNode(pagenode)
+                    
         if mode == "pureXml":
               # first div contains text
-              pagedivs = pagedom.xpath("/div")
+              pagedivs = dom.xpath("/div")
               if len(pagedivs) > 0:
                   pagenode = pagedivs[0]
                   return serializeNode(pagenode)      
         # text-with-links mode
         if mode == "text_dict":
             # first div contains text
-            pagedivs = pagedom.xpath("/div")
+            pagedivs = dom.xpath("/div")
             if len(pagedivs) > 0:
                 pagenode = pagedivs[0]
                 # check all a-tags
@@ -203,18 +352,33 @@ class MpdlXmlTextServer(SimpleItem):
                             # add target
                             l.setAttributeNS(None, 'target', '_blank')
                             l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=700, scrollbars=1'); return false;")
-                            l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')      
+                            l.setAttributeNS(None, 'onClick', 'popupWin.focus();')      
                         if href.startswith('lt/lemma.xql'):    
                             selfurl = self.absolute_url()
                             hrefNode.nodeValue = href.replace('lt/lemma.xql','%s/template/head_main_lemma'%selfurl)
                             l.setAttributeNS(None, 'target', '_blank')
                             l.setAttributeNS(None, 'onClick',"popupWin = window.open(this.href, 'contacts', 'location,width=500,height=600,top=180, left=700, scrollbars=1'); return false;")
-                            l.setAttributeNS(None, 'onDblclick', 'popupWin.focus();')   
+                            l.setAttributeNS(None, 'onClick', 'popupWin.focus();')   
                         if href.startswith('#note-'):
                             hrefNode.nodeValue = href.replace('#note-',"?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&pn=%s#note-"%(url,viewMode,tocMode,tocPN,pn))    
                 return serializeNode(pagenode)
         return "no text here"
-
+    
+    def getText(self, mode="text", pn=1, docinfo=None, pageinfo=None):
+        data = self.getTextPage(mode="text", pn=1 ,docinfo=docinfo, pageinfo=pageinfo)
+        logging.debug("TEXT ALL data: %s"%(data))
+        return data
+    
+    def getXML(self, mode="xml", pn=1, docinfo=None, pageinfo=None):
+        data = self.getTextPage(mode="xml", pn=1 ,docinfo=docinfo, pageinfo=pageinfo)
+        logging.debug("TEXT ALL data: %s"%(data))
+        return data
+    
+    def getDictionary(self, mode="text_dict", pn=1, docinfo=None, pageinfo=None):
+        data = self.getTextPage(mode="text_dict", pn=1 ,docinfo=docinfo, pageinfo=pageinfo)
+        logging.debug("TEXT ALL data: %s"%(data))
+        return data
+    
     def getTranslate(self, query=None, language=None):
         """translate into another languages"""
         data = self.getServerData("lt/lex.xql","document=&language="+str(language)+"&query="+urllib.quote(query))
@@ -232,9 +396,9 @@ class MpdlXmlTextServer(SimpleItem):
         data = self.getServerData("lt/lemma.xql","document=&language="+str(language)+"&lemma="+urllib.quote(query))
         #pagexml=self.template.fulltextclient.eval("/mpdl/interface/lt/lemma.xql","document=&language="+str(language)+"&lemma="+url_quote(str(query)))
         return data
-
-    def getQuery (self,  docinfo=None, pageinfo=None, query=None, queryType=None, pn=1):
-         """number of"""
+    
+    def getQuery (self,  docinfo=None, pageinfo=None, query=None, queryType=None, pn=1, optionToggle=None):
+         #number of
          docpath = docinfo['textURLPath'] 
          pagesize = pageinfo['queryPageSize']
          pn = pageinfo['searchPN']
@@ -243,15 +407,15 @@ class MpdlXmlTextServer(SimpleItem):
          tocSearch = 0
          tocDiv = None
          
-         pagexml = self.getServerData("doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath, 'text', queryType, query, pagesize, pn))
-         #pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath, 'text', queryType, query, pagesize, pn) ,outputUnicode=False)
+         pagexml = self.getServerData("doc-query.xql","document=%s&mode=%s&queryType=%s&query=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath, 'text', queryType, urllib.quote(query), pagesize, pn))
          pagedom = Parse(pagexml)
          numdivs = pagedom.xpath("//div[@class='queryResultHits']")
          tocSearch = int(getTextFromNode(numdivs[0]))
+         logging.debug("documentViewer (gettoc) tocSearch: %s"%(tocSearch))
          tc=int((tocSearch/10)+1)
          logging.debug("documentViewer (gettoc) tc: %s"%(tc))
          return tc
-
+    
     def getToc(self, mode="text", docinfo=None):
         """loads table of contents and stores in docinfo"""
         logging.debug("documentViewer (gettoc) mode: %s"%(mode))
@@ -274,7 +438,7 @@ class MpdlXmlTextServer(SimpleItem):
         tocDiv = None
         
         pagexml = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn))
-        #pagexml=self.template.fulltextclient.eval("/mpdl/interface/doc-query.xql", "document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType,pagesize,pn), outputUnicode=False)
+        
         # post-processing downloaded xml
         pagedom = Parse(pagexml)
         # get number of entries
@@ -298,13 +462,16 @@ class MpdlXmlTextServer(SimpleItem):
         url = docinfo['url']
         selfurl = self.absolute_url()  
         viewMode=  pageinfo['viewMode']
+        characterNormalization = pageinfo ['characterNormalization']
+        optionToggle =pageinfo ['optionToggle']
         tocMode = pageinfo['tocMode']
         tocPN = pageinfo['tocPN']  
         
-        data = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s"%(docpath,queryType, pagesize, pn))  
-
-        page = data.replace('page-fragment.xql?document=%s'%str(path),'%s?url=%s&viewMode=%s&tocMode=%s&tocPN=%s'%(selfurl,url, viewMode, tocMode, tocPN))
+        data = self.getServerData("doc-query.xql","document=%s&queryType=%s&queryResultPageSize=%s&queryResultPN=%s&characterNormalization=regPlusNorm&optionToggle=1"%(docpath,queryType, pagesize, pn))  
+        page = data.replace('page-fragment.xql?document=%s'%str(path),'%s?url=%s&viewMode=%s&tocMode=%s&tocPN=%s&optionToggle=1'%(selfurl,url, viewMode, tocMode, tocPN))
         text = page.replace('mode=image','mode=texttool')
+        #logging.debug("documentViewer (characterNormalization) characterNormalization: %s"%(characterNormalization))
+        logging.debug("TEXT %s"%(text))
         return text
     
     def manage_changeMpdlXmlTextServer(self,title="",serverUrl="http://mpdl-proto.mpiwg-berlin.mpg.de/mpdl/interface/",timeout=40,RESPONSE=None):
@@ -326,7 +493,4 @@ def manage_addMpdlXmlTextServer(self,id,
     newObj = MpdlXmlTextServer(id,title,serverUrl,timeout)
     self.Destination()._setObject(id, newObj)
     if RESPONSE is not None:
-        RESPONSE.redirect('manage_main')
-
-
-    
+        RESPONSE.redirect('manage_main')
\ No newline at end of file